C#에서 OCR.net과 IronPDF를 활용하여 PDF OCR 워크플로우를 구축하는 방법

using IronPdf;

IronPdf.License.LicenseKey = "YOUR-LICENSE-KEY";

Imports IronPdf

IronPdf.License.LicenseKey = "YOUR-LICENSE-KEY"

using IronPdf;

// Create a PDF document with IronPDF
var renderer = new ChromePdfRenderer();

// Set 300 DPI for OCR accuracy -- higher DPI preserves text sharpness
renderer.RenderingOptions.PaperSize = IronPdf.Rendering.PdfPaperSize.A4;
renderer.RenderingOptions.DPI = 300;
renderer.RenderingOptions.MarginTop = 50;
renderer.RenderingOptions.MarginBottom = 50;

var pdf = renderer.RenderHtmlAsPdf(@"
    <h1>Document Report</h1>
    <p>Scene text integration for computer vision analysis.</p>
    <p>Text detection results for dataset and model analysis.</p>");

// Tag the document with searchable metadata
pdf.MetaData.Author = "OCR Processing Pipeline";
pdf.MetaData.Keywords = "OCR, Text Recognition, Computer Vision";
pdf.MetaData.ModifiedDate = DateTime.Now;

pdf.SaveAs("document-for-ocr.pdf");

// Export pages as PNG images for OCR.net -- 300 DPI is the recommended minimum
pdf.RasterizeToImageFiles("page-*.png", IronPdf.Imaging.ImageType.Png, 300);

Imports IronPdf

' Create a PDF document with IronPDF
Dim renderer As New ChromePdfRenderer()

' Set 300 DPI for OCR accuracy -- higher DPI preserves text sharpness
renderer.RenderingOptions.PaperSize = IronPdf.Rendering.PdfPaperSize.A4
renderer.RenderingOptions.DPI = 300
renderer.RenderingOptions.MarginTop = 50
renderer.RenderingOptions.MarginBottom = 50

Dim pdf = renderer.RenderHtmlAsPdf("
    <h1>Document Report</h1>
    <p>Scene text integration for computer vision analysis.</p>
    <p>Text detection results for dataset and model analysis.</p>")

' Tag the document with searchable metadata
pdf.MetaData.Author = "OCR Processing Pipeline"
pdf.MetaData.Keywords = "OCR, Text Recognition, Computer Vision"
pdf.MetaData.ModifiedDate = DateTime.Now

pdf.SaveAs("document-for-ocr.pdf")

' Export pages as PNG images for OCR.net -- 300 DPI is the recommended minimum
pdf.RasterizeToImageFiles("page-*.png", IronPdf.Imaging.ImageType.Png, 300)

using System;
using System.Net.Http;
using System.Threading.Tasks;

// Queue-based OCR processing with exponential backoff retry
async Task<string> ProcessOcrWithRetry(string imagePath, int maxRetries = 3)
{
    for (int attempt = 0; attempt < maxRetries; attempt++)
    {
        try
        {
            // Replace with your actual OCR.net API call
            return await CallOcrNetApi(imagePath);
        }
        catch (HttpRequestException ex) when (ex.Message.Contains("429"))
        {
            if (attempt == maxRetries - 1) throw;
            var delay = TimeSpan.FromSeconds(Math.Pow(2, attempt));
            await Task.Delay(delay);
        }
    }
    throw new InvalidOperationException("OCR processing failed after all retries");
}

Imports System
Imports System.Net.Http
Imports System.Threading.Tasks

' Queue-based OCR processing with exponential backoff retry
Async Function ProcessOcrWithRetry(imagePath As String, Optional maxRetries As Integer = 3) As Task(Of String)
    For attempt As Integer = 0 To maxRetries - 1
        Try
            ' Replace with your actual OCR.net API call
            Return Await CallOcrNetApi(imagePath)
        Catch ex As HttpRequestException When ex.Message.Contains("429")
            If attempt = maxRetries - 1 Then Throw
            Dim delay As TimeSpan = TimeSpan.FromSeconds(Math.Pow(2, attempt))
            Await Task.Delay(delay)
        End Try
    Next
    Throw New InvalidOperationException("OCR processing failed after all retries")
End Function

using IronPdf;
using System;
using System.Collections.Generic;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

// --- Stage 1: Export PDF pages as images for OCR ---
var scannedPdf = PdfDocument.FromFile("input-document.pdf");
var imageFiles = scannedPdf.RasterizeToImageFiles(
    "scan-page-{0}.png",
    IronPdf.Imaging.ImageType.Png,
    300 // 300 DPI -- minimum for reliable OCR accuracy
);

// --- Stage 2: Process each image through OCR.net ---
var ocrResults = new List<string>();
foreach (var imageFile in imageFiles)
{
    // Replace this placeholder with your actual OCR.net API integration
    string ocrText = await SendImageToOcrNet(imageFile);
    ocrResults.Add(ocrText);
}

// --- Stage 3: Reassemble recognized text as a searchable PDF ---
var htmlBuilder = new StringBuilder();
htmlBuilder.Append(@"<!DOCTYPE html><html><head>
    <style>body{font-family:Arial,sans-serif;margin:40px;}
    .page{page-break-after:always;} pre{white-space:pre-wrap;}</style>
    </head><body>");

for (int i = 0; i < ocrResults.Count; i++)
{
    htmlBuilder.AppendFormat(
        "<div class='page'><h2>Page {0}</h2><pre>{1}</pre></div>",
        i + 1,
        System.Web.HttpUtility.HtmlEncode(ocrResults[i])
    );
}
htmlBuilder.Append("</body></html>");

var renderer = new ChromePdfRenderer();
renderer.RenderingOptions.DPI = 300;
renderer.RenderingOptions.EnableJavaScript = false;

var searchablePdf = await renderer.RenderHtmlAsPdfAsync(htmlBuilder.ToString());
searchablePdf.MetaData.Title = "OCR Processed Document";
searchablePdf.MetaData.Subject = "Searchable PDF from OCR";
searchablePdf.MetaData.CreationDate = DateTime.UtcNow;
searchablePdf.SecuritySettings.AllowUserPrinting = true;
searchablePdf.SecuritySettings.AllowUserCopyPasteContent = true;

searchablePdf.SaveAs("searchable-document.pdf");

Imports IronPdf
Imports System
Imports System.Collections.Generic
Imports System.Net.Http
Imports System.Text
Imports System.Threading.Tasks

' --- Stage 1: Export PDF pages as images for OCR ---
Dim scannedPdf = PdfDocument.FromFile("input-document.pdf")
Dim imageFiles = scannedPdf.RasterizeToImageFiles(
    "scan-page-{0}.png",
    IronPdf.Imaging.ImageType.Png,
    300 ' 300 DPI -- minimum for reliable OCR accuracy
)

' --- Stage 2: Process each image through OCR.net ---
Dim ocrResults As New List(Of String)()
For Each imageFile In imageFiles
    ' Replace this placeholder with your actual OCR.net API integration
    Dim ocrText As String = Await SendImageToOcrNet(imageFile)
    ocrResults.Add(ocrText)
Next

' --- Stage 3: Reassemble recognized text as a searchable PDF ---
Dim htmlBuilder As New StringBuilder()
htmlBuilder.Append("<!DOCTYPE html><html><head>
    <style>body{font-family:Arial,sans-serif;margin:40px;}
    .page{page-break-after:always;} pre{white-space:pre-wrap;}</style>
    </head><body>")

For i As Integer = 0 To ocrResults.Count - 1
    htmlBuilder.AppendFormat(
        "<div class='page'><h2>Page {0}</h2><pre>{1}</pre></div>",
        i + 1,
        System.Web.HttpUtility.HtmlEncode(ocrResults(i))
    )
Next
htmlBuilder.Append("</body></html>")

Dim renderer As New ChromePdfRenderer()
renderer.RenderingOptions.DPI = 300
renderer.RenderingOptions.EnableJavaScript = False

Dim searchablePdf = Await renderer.RenderHtmlAsPdfAsync(htmlBuilder.ToString())
searchablePdf.MetaData.Title = "OCR Processed Document"
searchablePdf.MetaData.Subject = "Searchable PDF from OCR"
searchablePdf.MetaData.CreationDate = DateTime.UtcNow
searchablePdf.SecuritySettings.AllowUserPrinting = True
searchablePdf.SecuritySettings.AllowUserCopyPasteContent = True

searchablePdf.SaveAs("searchable-document.pdf")